English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The field of generative image inpainting and object insertion has madesignificant progress with the recent advent of latent diffusion models.Utilizing a precise object mask can greatly enhance these applications.However, due to the challenges users encounter in creating high-fidelity masks,there is a tendency for these methods to rely on more coarse masks (e.g.,bounding box) for these applications. This results in limited control andcompromised background content preservation. To overcome these limitations, weintroduce SmartMask, which allows any novice user to create detailed masks forprecise object insertion. Combined with a ControlNet-Inpaint model, ourexperiments demonstrate that SmartMask achieves superior object insertionquality, preserving the background content more effectively than previousmethods. Notably, unlike prior works the proposed approach can also be usedeven without user-mask guidance, which allows it to perform mask-free objectinsertion at diverse positions and scales. Furthermore, we find that when usediteratively with a novel instruction-tuning based planning model, SmartMask canbe used to design detailed layouts from scratch. As compared with user-scribblebased layout design, we observe that SmartMask allows for better qualityoutputs with layout-to-image generation methods. Project page is available athttps://smartmask-gen.github.io

SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control